Comments on: Lessfs-1.6.0-beta0 has been released.

By: gwpl

gwpl — Fri, 23 Mar 2012 22:19:27 +0000

“By default Lessfs will now compile with berkeleydb instead of tokyocabinet.” – Could you be more specific, what were the reasons for such decision? (Or link to related materials, like mailinglist discussions?)

Currently there is successor of Tokyo Cabinet , which is Kyoto Cabinet. Have you considered it ?

What are practical implication of switching LessFS from Tokyo Cabinet to berkeleydb ? I am most curious about performance.

Thanks in advance for all info and pointing to right places. I’d love to read more about details related under the cover of this stuff.

Best,
Grzegorz

By: bsd

bsd — Thu, 19 Jan 2012 20:20:32 +0000

Great ! Sounds promising…

By: Mark Ruijter

Mark Ruijter — Wed, 18 Jan 2012 07:56:27 +0000

Thanks for making me aware that there even is something like LZ4.
I just looked into it and it appears to be promising. On average the speeds appear to be 48% faster then snappy.
This is amazing since snappy has proved to be 30% faster then QuickLZ which once was the fastest compression protocol.

http://fastcompression.blogspot.com/
https://issues.apache.org/jira/browse/HADOOP-7657?focusedCommentId=13170733&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-13170733

Porting a new compression algorithm to Lessfs is very simple.
So when I have time I’ll give it a go so we can see if LZ4 lives up to it’s promise.

Thanks,

Mark.

By: bsd

bsd — Tue, 17 Jan 2012 21:52:53 +0000

Have you had time to test LZ4 and compare it to Snappy ?